相关论文: Improving Adversarial Data Collection by Supportin…

We introduce a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure. We show that training models on this new dataset leads to state-of-the-art performance on a variety of…

The classification of acoustic environments allows for machines to better understand the auditory world around them. The use of deep learning in order to teach machines to discriminate between different rooms is a new area of research.…

Generative Adversarial Networks (GANs) have shown impressive results in various image synthesis tasks. Vast studies have demonstrated that GANs are more powerful in feature and expression learning compared to other generative models and…

Reading comprehension models often overfit to nuances of training datasets and fail at adversarial evaluation. Training with adversarially augmented dataset improves robustness against those adversarial attacks but hurts generalization of…

Adversarial training (AT) is widely considered the state-of-the-art technique for improving the robustness of deep neural networks (DNNs) against adversarial examples (AE). Nevertheless, recent studies have revealed that adversarially…

Annotator disagreement is ubiquitous in natural language processing (NLP) tasks. There are multiple reasons for such disagreements, including the subjectivity of the task, difficult cases, unclear guidelines, and so on. Rather than simply…

Adversarial examples are maliciously modified inputs created to fool deep neural networks (DNN). The discovery of such inputs presents a major issue to the expansion of DNN-based solutions. Many researchers have already contributed to the…

Adversarial examples are inputs for machine learning models that have been designed by attackers to cause the model to make mistakes. In this paper, we demonstrate that adversarial examples can also be utilized for good to improve the…

The rise of emergence of social media platforms has fundamentally altered how people communicate, and among the results of these developments is an increase in online use of abusive content. Therefore, automatically detecting this content…

Word-level adversarial attacks have shown success in NLP models, drastically decreasing the performance of transformer-based models in recent years. As a countermeasure, adversarial defense has been explored, but relatively few efforts have…

Standard accuracy metrics indicate that reading comprehension systems are making rapid progress, but the extent to which these systems truly understand language remains unclear. To reward systems with real language understanding abilities,…

In retrieval-based dialogue systems, a response selection model acts as a ranker to select the most appropriate response among several candidates. However, such selection models tend to rely on context-response content similarity, which…

Adversarial examples are data points misclassified by neural networks. Originally, adversarial examples were limited to adding small perturbations to a given image. Recent work introduced the generalized concept of unrestricted adversarial…

Data augmentation is widely used in text classification, especially in the low-resource regime where a few examples for each class are available during training. Despite the success, generating data augmentations as hard positive examples…

Generated hateful and toxic content by a portion of users in social media is a rising phenomenon that motivated researchers to dedicate substantial efforts to the challenging direction of hateful content identification. We not only need an…

Images posted online present a privacy concern in that they may be used as reference examples for a facial recognition system. Such abuse of images is in violation of privacy rights but is difficult to counter. It is well established that…

Neural networks are susceptible to adversarial examples-small input perturbations that cause models to fail. Adversarial training is one of the solutions that stops adversarial examples; models are exposed to attacks during training and…

The ubiquity of social media has transformed online interactions among individuals. Despite positive effects, it has also allowed anti-social elements to unite in alternative social media environments (eg. Gab.com) like never before.…

Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To…

The design of additive imperceptible perturbations to the inputs of deep classifiers to maximize their misclassification rates is a central focus of adversarial machine learning. An alternative approach is to synthesize adversarial examples…